Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4520baad3f6b69630065cdafd5c5b37d97d73083631718eb2d3f930865f247b
+oid sha256:161429549ad046c92c0830348f3519a81c9695140c076ba86819b63651deff64
 size 498615900

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6852a54b62e1d649e6a859cd34725af91411a6e5cb31c94b824235999d27ae02
+oid sha256:303573cf617fd5524986ae8dd755826ae69c14b6d66df9a27c6e00700c7f2ce6
 size 997351674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:694f423926ac4340014289d665fb41e7c4dde468bc19fcd2c2b612fc44bafec6
+oid sha256:47899d438bc1e8e9d368d92fe5b1946e59435e7701dd92edc87bdef54734dd67
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877229026b55d004235a151c979fd49f2e0a0f7eab8421f7dbe46ed565dd74f6
+oid sha256:11342b2430a338f69f1320c6f8235ca7935daec91992c25666791c4e55f7a3d9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.57190397933845,
-  "best_model_checkpoint": "training_dir/checkpoint-500",
-  "epoch": 3.0,
+  "best_metric": 0.6211330799726014,
+  "best_model_checkpoint": "training_dir/checkpoint-1000",
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 750,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,25 @@
       "eval_samples_per_second": 46.846,
       "eval_steps_per_second": 5.856,
       "step": 750
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 61.78361129760742,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4837,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6359265734265734,
+      "eval_f1": 0.6211330799726014,
+      "eval_loss": 1.4274829626083374,
+      "eval_precision": 0.6772601484892057,
+      "eval_recall": 0.6359265734265734,
+      "eval_runtime": 48.713,
+      "eval_samples_per_second": 46.969,
+      "eval_steps_per_second": 5.871,
+      "step": 1000
     }
   ],
   "logging_steps": 500,
@@ -83,7 +102,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1251671639603616.0,
+  "total_flos": 1668780407351232.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null